Triple

T15693028
Position Surface form Disambiguated ID Type / Status
Subject Koursoum Mosque E380380 entity
Predicate namedAfter P63 FINISHED
Object Koursoum (local name)
Koursoum (local name) is the traditional local name associated with the historic Koursoum Mosque in Trikala, Greece.
 E1171073 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Koursoum (local name) | Statement: [Koursoum Mosque, namedAfter, Koursoum (local name)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koursoum (local name)
Context triple: [Koursoum Mosque, namedAfter, Koursoum (local name)]
  • A. Koum
    Koum is the surname of Jan Koum, the Ukrainian-American entrepreneur best known as the co-founder and former CEO of WhatsApp.
  • B. Mounana
    Mounana is a town in southeastern Gabon known historically for its uranium mining activities.
  • C. Mourou
    Mourou is the surname of Gérard Mourou, a French physicist and Nobel laureate known for pioneering chirped pulse amplification in laser physics.
  • D. Korandjé
    Korandjé is a highly endangered Northern Songhay language spoken in the oasis town of Tabelbala in southwestern Algeria.
  • E. Kouneli
    Kouneli is a small Greek island in the Echinades group in the Ionian Sea.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Koursoum (local name)
Triple: [Koursoum Mosque, namedAfter, Koursoum (local name)]
Generated description
Koursoum (local name) is the traditional local name associated with the historic Koursoum Mosque in Trikala, Greece.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koursoum (local name)
Target entity description: Koursoum (local name) is the traditional local name associated with the historic Koursoum Mosque in Trikala, Greece.
  • A. Koum
    Koum is the surname of Jan Koum, the Ukrainian-American entrepreneur best known as the co-founder and former CEO of WhatsApp.
  • B. Mounana
    Mounana is a town in southeastern Gabon known historically for its uranium mining activities.
  • C. Mourou
    Mourou is the surname of Gérard Mourou, a French physicist and Nobel laureate known for pioneering chirped pulse amplification in laser physics.
  • D. Korandjé
    Korandjé is a highly endangered Northern Songhay language spoken in the oasis town of Tabelbala in southwestern Algeria.
  • E. Kouneli
    Kouneli is a small Greek island in the Echinades group in the Ionian Sea.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f4f5a888190bd3681bcb9bbc02f completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6eed9a8c8190a57ffce61a27ec17 completed May 9, 2026, 5:29 p.m.
NEDg Description generation batch_69ff7097adec8190ad5fc00fa57e3383 completed May 9, 2026, 5:36 p.m.
NED2 Entity disambiguation (via description) batch_69ff70f97eec8190a1f5affdad31f2b2 completed May 9, 2026, 5:38 p.m.
Created at: April 10, 2026, 4:44 a.m.